Content generation system and method

Abstract

A content generation system operable to generate one or more actions to be performed by an agent, the system comprising an input receiving unit operable to receive information defining an input action, the input action being an action associated with the agent, a constraint identifying unit operable to identify one or more constraints associated with the input action, and an action generation unit operable to generate, using a machine learning model, one or more actions in dependence upon the information defining the input action and the identified constraints wherein the one or more actions are variations of the defined action.

1 . A content generation system operable to generate one or more actions to be performed by an agent, the system comprising:
 an input receiving unit operable to receive information defining an input action, the input action being an action associated with the agent;   a constraint identifying unit operable to identify one or more constraints associated with the input action; and   an action generation unit operable to generate, using a machine learning model, one or more actions in dependence upon the information defining the input action and the identified constraints wherein the one or more actions are variations of the defined action.   
     
     
         2 . The system of  claim 1 , wherein the input receiving unit is operable to receive information defining a plurality of input actions that are functionally equivalent. 
     
     
         3 . The system of  claim 1 , wherein the received information comprises one or more of video content, animations, wire-frame models and motion information, and parametric information defining the input action. 
     
     
         4 . The system of  claim 1 , wherein one or more constraints are defined in the received information. 
     
     
         5 . The system of  claim 1 , wherein one or more constraints are derived in dependence upon the input action. 
     
     
         6 . The system of  claim 1 , wherein one or more constraints define contact points of the agent with one or more external elements or surfaces. 
     
     
         7 . The system of  claim 1 , wherein one or more constraints relate to one or more functional and/or stylistic aspects of the input action. 
     
     
         8 . The system of  claim 1 , wherein one or more constraints define an acceptable eccentricity of the generated actions with respect to an input action. 
     
     
         9 . The system of  claim 1 , comprising an action output unit operable to output one or more of the generated actions to a storage unit and/or a computer game. 
     
     
         10 . The system of  claim 1 , comprising a content output unit operable to execute gameplay of game in dependence upon user inputs, the gameplay comprising the agent performing one or more of the generated actions. 
     
     
         11 . The system of  claim 10 , wherein the content output unit is operable to monitor user performance within the game and to substitute the generated actions for corresponding input actions in dependence upon variations in user performance. 
     
     
         12 . A content generation method for generating one or more actions to be performed by an agent, the method comprising:
 receiving information defining an input action, the input action being an action associated with the agent;   identifying one or more constraints associated with the input action; and   generating, using a machine learning model, one or more actions in dependence upon the information defining the input action and the identified constraints wherein the one or more actions are variations of the defined action.   
     
     
         13 . A non-transitory machine-readable storage medium which stores computer software which, when executed by a computer, causes the computer to perform a method for generating one or more actions to be performed by an agent, the method comprising:
 receiving information defining an input action, the input action being an action associated with the agent;   identifying one or more constraints associated with the input action; and   generating, using a machine learning model, one or more actions in dependence upon the information defining the input action and the identified constraints wherein the one or more actions are variations of the defined action.